Sonar Reasoning Pro is an AI model by Perplexity. View detailed benchmark scores, pricing data, and performance metrics on Serenities AI Models.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
Speed Benchmarks
Cost Benchmarks
Context Benchmarks
Available from 8 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 3 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| DevPass (LLM Gateway) | $2 | $8 | — | 128K | — |
| Eden AI | $2 | $8 | — | 128K | — |
| LLM Gateway | $2 | $8 | — | 128K | — |
| OpenRouter | $2 | $8 | — | 128K | Supported |
| Opper | $2 | $8 | — | 128K | — |
| Perplexity | $2 | $8 | — | 128K | Supported |
| AnyAPI | — | — | — | 128K | — |
| Vercel AI Gateway | — | — | — | 127K | Supported |
Sonar Reasoning Pro — Frequently Asked Questions
How much does Sonar Reasoning Pro cost?
Sonar Reasoning Pro costs $2.0 per 1M input tokens and $8.0 per 1M output tokens. This is mid-range pricing for its capability level.
How fast is Sonar Reasoning Pro?
Sonar Reasoning Pro generates output at 22 tokens per second, which is slower, prioritizing quality over speed compared to other models. The time to first token is 2380 ms.
What is the context window of Sonar Reasoning Pro?
Sonar Reasoning Pro has a context window of 128K tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created Sonar Reasoning Pro?
Sonar Reasoning Pro was created by Perplexity. It is classified as a flagship model in our catalogue.
Is Sonar Reasoning Pro open source?
No, Sonar Reasoning Pro is a proprietary model. It is available through Perplexity's API and compatible providers.